Short-Length Code Designs for Integrated Sensing and Communications: A Deep Learning Approach

2026-09-27

AI Summary

This study addresses the challenging trade-off between communication and sensing objectives in short-blocklength integrated sensing and communication (ISAC) waveform design by proposing an autoencoder-based non-coherent ISAC waveform design framework. Methodologically, a modified Cramér-Rao lower bound (CRLB) is derived and maximum-likelihood decoding rules are analyzed to reveal the structural coupling and performance trade-off mechanisms between the dual functionalities, which subsequently enables joint optimization via deep learning. Experimental results demonstrate that the proposed framework significantly enhances both communication reliability and sensing accuracy under short blocklengths and channel fading conditions. Overall, this work provides effective theoretical foundations and methodological support for the design of non-coherent ISAC systems.

Abstract

Integrated sensing and communication (ISAC) enables joint communication and sensing using a shared waveform, but its signal design is challenging due to the inherent trade-off between the two objectives, particularly in the short blocklength regime. This paper proposes an autoencoder (AE)-based framework for ISAC waveform design in noncoherent settings. We derive a modified Cram\'er-Rao bound for multi-target delay estimation and analyze the maximum-likelihood decoding rule for noncoherent communication under correlated fading. These results reveal structural connections and trade-offs between communication and sensing objectives in waveform design. Based on this analysis, the AE learns waveform representations that jointly optimize both functionalities, with a tunable parameter controlling the trade-off. Simulation results show that the proposed design outperforms conventional schemes in both communication reliability and sensing accuracy, especially under short blocklength and fading conditions.

Problem

• Integrated Sensing and Communications
• Short blocklength
• Waveform design
• Noncoherent settings
• Trade-off

Innovation

• Integrated Sensing and Communications
• Autoencoder
• Short Blocklength
• Noncoherent Waveform Design
• Modified Cramér-Rao Bound